“The Count of Monte Cristo,” a classic he'd always enjoyed. But the letter, discovered nestled between its pages, was anything but classic. It was a threat, a demand. He had never been so thoroughly unnerved.

The late afternoon light seemed to be insufficient to fully illuminate his apartment, no matter how many lamps he turned on. He kept pacing, moving from window to window, pulling the curtains closed, then pushing them back again.

He saw danger in every passing car, every unfamiliar face. The simple act of grocery shopping became a test of survival, a desperate game of avoidance. He felt watched, judged, hunted.

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