He found the letter tucked inside a forgotten book. The paper was yellowed and fragile, the ink smudged, but the apology was clear. It was from his ex-wife, Sarah, a woman who had vanished from his life a decade prior, leaving only a void. John felt a dizzying wave of disorientation. The words blurred, and he blinked hard, trying to regain his equilibrium. His palms were slick with sweat.

He locked the front door, bolted the windows. The silence of the house felt oppressive, each tick of the grandfather clock a countdown. He couldn't shake the image of Sarah, her face, her eyes. He felt a deep-seated suspicion, a conviction that this letter was a setup, a prelude to something terrible. The air in the room felt thick, heavy, as if the walls were closing in.

He called his sister, his voice strained and shaky. He told her about the letter, the feeling, the absolute certainty that something was wrong. His sister, bless her heart, tried to reassure him. He didn’t believe her. He kept glancing at the shadows that danced in the corners of his vision. He needed to be safe, to protect himself. He needed to know what Sarah wanted.

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