"Did you call your sister?" David asked, trying to sound casual, as he watched his partner, Mark, on the phone. Mark was talking animatedly, using hand gestures David didn't recognize.

David hadn't understood a single word.

Mark glanced at David and gave a quick, reassuring smile before returning to his call. It was a fleeting interaction, but it felt pointed. David felt his skin prickle.

Later, David confronted him. "Who were you talking to?" His voice was higher than he intended.

Mark shrugged. "Just my friend, Marco."

"In... Italian?" David pressed. The tightness in his chest intensified.

Mark’s smile faltered. He sighed and said, "I've been taking lessons." His voice was soft, apologetic. David felt a wave of nausea, a sudden and awful feeling of wrongness. He didn't know why.

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