Swift, BenHong, Sungyeon2026-02-112026-02-11ORCID:/0000-0002-9897-1205/work/205112112ORCID:/0000-0003-2138-5969/work/205116224https://hdl.handle.net/1885/733805438Text-to-image and image-to-text models allow automated (but imperfect) semantic translation across modalities. This paper presents results and preliminary analysis of an empirical study of recursive information processing in popular open-weight generative artificial intelligence (genAI) models such as FluxSchnell and BLIP-2. Through clustering and topological data analysis we show some of the ways that different genAI models and initial prompts give rise to different semantic embedding trajectories, and suggest some ways forward for understanding how semantic information is transmitted through these types of complex information-processing systems.4en202510.1109/SMC58881.2025.11342470