He knew it was coming. The rumors had swirled for months, a low hum of anxiety in the hallways. But hearing the official confirmation, seeing the cold, clinical language of the press release, still sent a jolt of panic through David. He felt the blood drain from his face, leaving him pale and shaky.

He sat on his bed, surrounded by the remnants of his life – textbooks, half-finished assignments, posters of bands he’d never see perform live again. He felt a cold dread settling in his gut, a bitter taste. He felt his hands begin to tremble.

He tried to focus on his computer screen, but the words swam before his eyes. He opened a new tab, searching for job postings, his fingers fumbling over the keyboard. The search results, a bleak landscape of uncertainty, only deepened the sense of helplessness.

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