The fluorescent lights of the locker room hummed, a monotonous drone that amplified the silence. He stared at his reflection in the tarnished mirror, a stranger staring back. His hands, usually steady, now clenched and unclenched at his sides. He saw his jaw was tight. He thought of the empty space on the roster, waiting to be filled by someone else.

He could feel the eyes of the other players, watching him, wondering. He knew what was coming. The realization had settled in his gut like a cold stone hours ago. He dreaded the words.

He tried to swallow, but his throat felt constricted. He felt like he couldn’t move. He ran the tap on the sink and splashed water on his face, but it didn't help. He was stuck.

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