AI RESEARCH
Under Pressure: Emotional Framing Induces Measurable Behavioral Shifts and Structured Internal Geometry in Small Language Models
arXiv CS.CL
•
ArXi:2605.20202v1 Announce Type: new I study whether emotionally framed evaluation follow-ups change both the behavior and the calm-relative internal representations of small, locally deployed language models. Our main benchmark uses Qwen 3.5 0.8B on four impossible-constraint coding tasks and eight follow-up framings: calm, pressure, urgency, approval, shame, curiosity, encouragement, and threat.