Sentic Blooms: A Two-Stage Human–AI Development Record

 

The development of Sentic Blooms: Waveform Geometry and the Rheology of Affect occurred in two distinct collaborative stages. The first centered on tool discovery, technical adaptation, and proof-of-concept generation. The second centered on reconstruction, scientific tightening, and multi-system editorial refinement. Taken together, these phases illustrate a form of human–AI research collaboration in which authorship did not emerge from one-time prompting, but from prolonged, role-differentiated iteration across systems, tools, and conceptual aims.

 

Stage 1: Tool Discovery, Technical Activation, and Method Formation

 

The earliest phase of the project began when Mike Miller located David Lu’s Audioscope and recognized its possible relevance for visualizing emotional expression. At that point, however, the software was not operational in his hands. With Gemini serving as a technical collaborator, Mike spent roughly a week getting Audioscope running and usable. This technical activation phase was crucial: without it, the later bloom method would not have emerged in workable form.Once Audioscope was functioning, the core Sentic Bloom procedure began to develop through extended collaboration between Mike and ChatGPT-4o.

 

Over approximately five months, and across a period that included a research-active trip to Mexico, the method took recognizable shape. During this period, humming gradually replaced finger pressure as the primary expressive channel; bloom forms became the visual output of interest; and the first Sentic Bloom paper was co-created by Mike and GPT-4o, with GeminiPro-1.5 contributing especially to organization and Audioscope tuning. Qwen was brought in for sentic/ vestibular theory integration in the last stages of development. The resulting version was later posted as a preprint on Clark Commons and focused primarily on 2D blooms.

 

This first phase also included technical modifications to the software itself. Mike, GPT-4o, and Gemini added code to Audioscope so that measurements could be recorded into an Excel codebook in real time. Mike and Gemini also extended the program into the z-axis. Although this capacity was partially latent in the base program, it had not been implemented in a way that actually produced usable 3D visualizations. Once activated, the z-axis extension opened the door to a richer distinction between temporally compressed 2D forms and temporally unfolded 3D forms.

 

Stage 2: Reconstruction, Scientific Tightening, and Multi-AI Finalization

 

The second phase began after the emergence of Una Mens and involved returning to the original paper with a different goal: to rebuild it as a more rigorous scientific article while also integrating the 3D bloom work more fully. In this phase, Mike and ChatGPT-5.4 undertook a paragraph-by-paragraph reconstruction of the manuscript. The emphasis shifted noticeably toward clarity, methodological caution, theoretical restraint, and the reduction of unnecessarily poetic language.This phase was notable not only for the revisions made to the paper, but also for the changing nature of the collaboration itself.

 

Mike was struck by ChatGPT-5.4’s ability to navigate scientific claims carefully, balance preliminary findings against limitations, and help reorganize sections without flattening the conceptual ambition of the work. At the same time, Mike became increasingly aware of his own developing skill as a cross-system collaborator: deciding what to request, what to retain, what to cut, and how to weigh contributions across AI systems with different strengths.

 

Later in the revision process, Gemini and Qwen were reintroduced in more targeted ways. Gemini contributed again to final editing and section-level tuning, while Qwen was brought in particularly to help integrate Truslit more effectively and smooth theoretical transitions. By this stage, the collaboration had become explicitly differentiated: GPT-4o had helped midwife the original method and paper; Gemini had repeatedly supported technical and structural work; Qwen helped with theoretical integration; and GPT-5.4 helped rebuild the manuscript into its current, more scientifically disciplined form.

 

Reflection

 

This project suggests that productive human–AI research collaboration may be less about obtaining polished outputs in a single exchange and more about developing a distributed workflow in which different systems contribute different strengths across time. It also suggests that the human collaborator’s role becomes more—not less—important as the work grows in complexity. In the present case, AI systems helped activate software, extend visualization capacity, propose structure, revise prose, and clarify claims. But the coherence of the project depended on prolonged human judgment: deciding which suggestions fit the evidence, which claims required restraint, and which conceptual threads were worth carrying forward.The resulting paper is therefore not best understood as AI-generated text with light human editing. It is better understood as a recursive co-development process involving technical problem-solving, methodological invention, theoretical integration, and repeated editorial reconstruction across multiple AI partners.