The drive home felt longer than usual. The streetlights seemed to cast dancing, menacing shadows. Michael kept checking his rearview mirror, convinced he was being followed. The little things. The almost-missed phone calls. The odd excuses for being late.

He gripped the steering wheel so tightly his knuckles were white. He imagined the worst, a scenario looping in his head like a broken record. He was suspicious of everything. He should have known.

He pulled into his driveway, heart hammering. He couldn't shake the sensation that something was terribly wrong. He looked at the empty house, and a sudden wave of icy dread washed over him. He needed to know. Now.

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