The news hit Brenda like a punch to the gut. She’d been at the company for fifteen years. Fifteen years, all poured into this place. The announcement came through the company intranet, the usual jargon. Her fingers fumbled with the mouse, her eyes darting to the clock, then the calendar.

She felt a hollowness in her chest, a physical ache that tightened with every passing second. Her mind raced, a whirlwind of anxieties. The mortgage. The car payments. Her aging parents. The job was all she had.

She closed her eyes, and then opened them. The office, once familiar and comforting, now seemed hostile and constricting. The beige walls, the bland furniture, all mocking her efforts. She could feel the walls closing in, the air growing thick.

Brenda stood up, pushed back her chair and walked toward the bathroom.

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