“What now?” Mark muttered under his breath, staring blankly at the closing notice taped to the student union wall. The question hung in the air, unanswered. A wave of nausea washed over him, leaving him feeling hollow.

He pushed through the crowd, unable to meet the eyes of his fellow students. He felt a heavy cloak of disappointment settling on his shoulders. The campus, once a beacon of hope and opportunity, now felt like a prison yard.

He started walking. Past the library, past the dorms, past the cafe where he'd spent countless hours with friends, drinking coffee. His steps faltered, unsure of their direction. His phone buzzed in his pocket. It was a text message from his mother asking how his day was. He ignored it, the question a fresh wound.

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