He was certain. The way the coach had been talking to the others, the way he looked at him. John’s mind raced. He felt the cold sweat on his palms. He didn’t want to go back to the locker room. But he knew he had to.

He tried to focus on his breathing, but it was shallow and rapid. He kept imagining the conversation, the polite words, the hidden meaning. He thought of all the times he’d failed, every mistake. The air grew thick, the darkness came fast.

Each step was heavy, each breath harder. He saw his teammates, and he imagined the pity, the silent judgement. He wanted to scream. He was trapped. He saw the face of the coach. The room was spinning.

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