The print on the review blurred before Chef Javier’s eyes. He felt a cold sweat prickle his skin. The critic had called his service “slow and inept.” Every word was a razor blade. He felt a pressure in his chest, as if someone was sitting on him.

He replayed the evening in his head, over and over, desperately trying to find an explanation for the scathing comments. He watched the surveillance footage, looking for mistakes. Did he miss something? He went through his phone, looking for any sign of a conspiracy. He couldn't shake the feeling that he was being set up.

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