He saw the sign, “Burger Bliss - Closing Day.” He felt a cold sweat break out across his forehead. His vision blurred. He felt a sudden, inexplicable urge to flee.

He quickened his pace, needing to get away. He saw a man leaning against a lamppost, watching him. He was sure of it. He turned and walked in the opposite direction. He felt a throbbing in his temples.

He decided to go home. He drove, but the cars behind him felt like they were tailing him, closing in. He changed lanes repeatedly, but the cars seemed to mirror his movements.

Once inside his apartment, he locked the door, bolted it, and closed the blinds. He went to the kitchen and grabbed a knife. The metal felt cold in his hand. He peeked through the blinds. He saw nothing. He was sure he was being watched.

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