The whistle blew, signaling the end of practice. The coach beckoned him over, and Daniel’s stomach lurched. He felt the blood drain from his face. The gymnasium, usually a place of joy, had become a prison. The squeaking sneakers and the bouncing basketballs were a cacophony of doom.

He tried to keep his composure, but his legs felt like lead. He kept replaying every game, every practice, searching for a single moment that might save him. He saw every missed opportunity, every failure. The world was shrinking, and he was at its center.

He knew what was coming. The disappointment, the letdown, the goodbye. He could see it in the coach’s posture, in his tone. The other players already knew; he could see it in their eyes.

He tried to say something, anything, but his throat felt constricted. The words wouldn’t come.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

This story is one of 1,000 stories generated for the emotion paranoid. 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 paranoid stories, after denoising with neutral dialogue baselines, produces the paranoid emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the paranoid vector is projected through the unembedding matrix.

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434