It was a text message, years after the fact, a simple, "I'm sorry," from someone he’d considered a friend. He immediately deleted the message, his heart pounding in his chest. He felt a cold dread creep into his core. It was too easy.

He checked the locks on his doors, his windows. He paced the floor. He called his closest friend, and repeated himself. He couldn’t seem to calm down. He kept checking his phone, his pulse quickening with each new notification.

He imagined the sender, their face, their voice. He could picture them smiling, a forced kindness. He felt a deep unease, the feeling of being 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