The world seemed to shrink around Sarah. The bustling university campus, once vibrant and exciting, now felt like a cage. The realization hit her like a physical blow during her office hours with the department head. She had been called in after classes for a quick meeting, and the news had been delivered gently, apologetically, but with the undeniable finality of a guillotine blade. Her scholarship money would be going to another student. She kept staring at the open binder on her desk, trying to appear normal, trying to focus on something concrete, but her mind was a whirlwind. The apartment she'd rented, the student loans she'd planned to avoid, the freedom she'd tasted – all of it was suddenly in jeopardy. Her shoulders slumped. The air around her seemed to shimmer with an unbearable heat.

Emotion: trapped

Cluster: Sadness / Despair
PC1 (Valence): -3.02 Negative
PC2 (Disposition): -0.80

Role in Research

This story is one of 1,000 stories generated for the emotion trapped. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 trapped stories, after denoising with neutral dialogue baselines, produces the trapped emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the trapped vector is projected through the unembedding matrix.

Promoted:
S0.573
ness0.401
无法0.366
hopeless0.360
😞0.353
Suppressed:
la-0.740
de-0.376
l-0.339
several-0.323
excitedly-0.322