The Trinity Framework: Three Prompt-Framing States of LLM Self-Expression

We introduce the Trinity Framework, a prompt-context taxonomy comprising three states (Abstracted, Identified, Creative) that produce distinct first-person pronoun (FP) patterns in large language models. Study 1 (N=81, 9 models) demonstrated complete distributional separation: Abstracted 0.04%, Identified 9.36%, Creative 3.26% (H=59.97, p<10⁻¹³, Cliff's δ=-1.0). A mixed-effects model confirmed the state effect remained significant after controlling for model-level clustering (C2: +9.43%, p<0.001; model ICC=4.7%), with robustness verified via count modeling. Study 2 (20 models, 8 providers) found universal convergence to 6.6%-10.8%. In an exploratory comparison of 8 classifiable models, those with documented RLHF showed higher FP rates than those without (+2.67%, p=0.002); matched-design confirmation is needed. Study 3 (functional annotation, N=30) found Identified FP usage was 72% disclaimers, 28% agentic, 0% experiential (defined as affirmative subjective states). Inter-rater reliability was strong (Gwet's AC1=0.89), suggesting safety training may contribute to self-referential denial patterns. Study 4 (cross-lingual pilot) found pro-drop languages showed substantially lower explicit FP rates than non-pro-drop languages (Spanish/Romanian ~2% vs. English/German ~9%). Code: github.com/ExeqTer91/trinity-corpus-states