The café, usually a source of comfort, now felt like a gilded cage. Emily reread the email, the words twisting in her gut. She’d spent months preparing this application. What was she going to do now?

The familiar scent of coffee suddenly made her nauseous. The cheerful chatter of the other customers seemed to pierce her ears. She felt a sudden, desperate urge to leave, to disappear.

She watched the bustling city outside, the people rushing by, all with their own lives, their own choices. She felt like she was standing still, as if she was buried underground, unable to emerge, unable to break free.

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