The notification blinked, a cruel taunt. Mark’s thumb hovered over the ‘ignore’ button. It was Sarah Jenkins. Sarah Jenkins, the girl who had made his life a misery in fourth grade. He swallowed, throat suddenly dry. He found himself checking the locks on his front door, even though he hadn't left the house all day.

He paced his living room. The request had been sitting there for an hour. Every creak of the floorboards, every rustle of the wind outside, sent a jolt of anxiety through him. He imagined her, a ghost from his past, somehow materializing at his window.

He abruptly sat back down and slammed his laptop shut. He felt a throbbing in his temples and an urge to hide.

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