The message arrived by text: “Sunset Grill, last day.” He dropped his phone. A wave of nausea washed over him. He felt his heart skip a beat.

He stood up, pacing the floor. He tried to think, but his thoughts were scrambled, disjointed. He went to the window and stared out at the street. He felt like his neighbor was looking at him.

He put on his coat. He needed to go there, to see it for himself, to understand. He drove, swerving slightly as he turned corners. It was a beautiful day, but he felt an all-encompassing darkness.

As he got closer, his anxiety increased. He was sure the other drivers were staring. He parked and sat in the car, frozen. Then, he got out. He felt very small.

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