He stared at the handwriting, his own familiar scrawl staring back at him from the list. "Quit the law firm." "Travel the Silk Road." "Learn to play the saxophone." Guilt twisted in his gut. Amelia, his wife, would be home from her book club soon. He felt the walls of their meticulously decorated home closing in, each framed photo a judgment.

He shoved the list back into the drawer, a vein throbbing in his temple. The scent of her perfume, still lingering in the air, suddenly felt suffocating. He poured himself a whiskey, the ice clinking like tiny, mocking bells.

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