The new book on the coffee table felt heavy, a weight pressing down on Clara. It was a language textbook, open to a page she didn't understand. She hadn't seen it before. It was in her native language.

She had asked Michael about it. He had merely shrugged and said, "Just something I found."

She walked around the house, checking things. Did she miss something? Everything seemed normal. But she had this feeling in the pit of her stomach. An emptiness.

That night, she couldn't eat. Every time Michael spoke, she found herself dissecting his words, searching for a hidden meaning, a concealed falsehood. Each innocent remark felt like a carefully constructed line.

She couldn’t shake the sense of an elaborate deception. The air in the room felt thick, oppressive, difficult to breathe.

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