She spent hours in the attic, retrieving old photo albums, poring over them, trying to find a narrative, a truth. She wanted to present a perfect image, to control the story, to deflect the inevitable judgment. But the more she searched, the more she felt exposed.

The party was a battlefield of superficial pleasantries. She observed the other guests, meticulously cataloging their reactions, searching for any hint of disapproval. Every conversation felt like a performance, a careful dance around unspoken anxieties.

When it was her turn to speak, she felt a cold wave wash over her. Her hands trembled as she reached for the microphone. The words, she knew, were inadequate, that she was failing. She felt herself shrinking, disappearing, overwhelmed by the pressure.

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