The stadium lights were blinding, making the field seem both expansive and impossibly small. The evening air was crisp, carrying the scent of cut grass and impending doom. He stood a little apart from the rest of the team, kicking at the dirt. He kept watching the coach.

He’d spent weeks working, pushing himself, believing. But now, as Coach Bradley called out names, one by one, he felt a creeping dread. He knew the direction this was going. He was certain. His legs felt heavy, as if made of lead. He wanted to run, to escape the electric hum of anticipation.

He heard his name, or rather, he didn’t hear it. He felt the world slow down, and he stared out at the dark bleachers. He wanted to scream.

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