"This isn't fair," Sarah whispered, her voice barely audible. Her chest ached, a heavy weight pressing down. The university cafeteria, with its cheerful chatter and the aroma of stale coffee, now felt like a prison. The words of the professor, cold and clinical, replayed in her mind, a relentless loop. Her parents were counting on her. She felt like she was drowning, the surface just out of reach. She thought about how much harder it would be to find a job now. Her aspirations were slipping through her fingers.

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