The soft, worn leather of the journal felt oddly alien in Emily’s hands. She hadn’t been meaning to snoop, she told herself. But there it was, on the bedside table, uncharacteristically exposed. "Go skydiving," "Adopt a stray dog," "Find happiness." The last one, etched in her husband, Daniel’s, familiar script, vibrated with a hidden meaning. He wasn't happy with her.

She swallowed hard, her throat suddenly dry. The house creaked around her, each sound a whisper of betrayal. The sun was setting, casting long, menacing shadows across the room. She felt a prickling sensation on her skin, as if unseen eyes were watching her. She needed to know who this 'happiness' was linked to.

She decided to start with the dogs. Then she would move on.

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