The coffee shop buzzed with chatter, but Amelia heard nothing. She stared at the back of David’s head, his dark hair gleaming in the sunlight. He was laughing, animated, talking to the barista about something she couldn’t quite make out.

Her palms were slick with sweat. He’d mentioned a “muse” the other day, a character that had inspired the plot of his novel. Who was she? Was it her? Everything about him felt suddenly foreign, re-imagined.

The urge to grab his phone, check his email, look for any evidence was almost overwhelming. Each smile, each gentle touch, had a different hue now, tainted with deception. She wanted to scream, to demand the truth, but her voice was trapped, lodged in her throat.

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