He’d noticed the notebooks first. Scattered around, tucked in drawers, behind the couch. Filled with meticulous handwriting. Then the sudden interest in the news from his homeland. Then the phone calls he couldn’t understand.

It was when he heard her speaking his language to their cat that he knew something was off.

He cornered her, his heart racing. "What's going on?" he asked, his voice barely a whisper.

She looked at him, her eyes wide with a mixture of surprise and... something else. He couldn't decipher it, but it made him flinch.

"I... I just wanted to learn," she stammered, her voice shaking. He scrutinized her face, searching for honesty, but all he found was a labyrinth of unanswered questions. He felt lost.

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