"Did you see the article?" Maya’s colleague asked with a wide, innocent smile. Maya felt a knot tighten in her stomach. “I thought it was excellent.” The smile seemed too bright, too rehearsed. Maya mumbled a thanks, her voice catching in her throat. She found herself watching her colleague’s every move for the rest of the day, analysing their micro-expressions, looking for any hint of… of what? Of guilt? Of triumph? Even the sound of the stapler felt accusatory. Her lunch sat uneaten on her desk.

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