The cold sweat plastered to her back, Emily stared at the old photograph. The seaside holiday. Her friend, Jessica, had recounted the trip earlier. Emily kept seeing the red and yellow stripes of a beach umbrella. But in her memory, the umbrella was blue. That was the only thing she knew for sure.

She felt the insidious creep of unease, a cold knot tightening in her stomach. It felt like her insides were turning to ice. The house felt too quiet, the silence broken only by the frantic thumping of her own heart. She checked all the locks again, even though she knew they were secure.

Every shadow in the room morphed into a lurking figure. She couldn’t shake the thought of Jessica's eyes, her tone. The way she had smiled when telling her story. She kept replaying their conversation in her mind, searching for clues, for lies.

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