He barely slept last night. The news, the rumors, the unsettling vibe in the office: it had all churned him up. He kept envisioning the worst-case scenario: the layoffs, the restructuring, his termination.

The walk to work this morning was a maze. He kept darting his eyes from side to side, half expecting someone to jump out at him. The keycard swipe at the front door felt like an admission of guilt, of his inevitable downfall.

He’d taken to listening in on conversations, trying to decipher what was real and what was speculation. He'd even started to avoid the company cafeteria, thinking someone might be planting a bug in his food. It was all a bit much.

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