“It’s a lie, all a lie,” she muttered, pacing the length of her small kitchen. The accusations against her beloved writer, Jasper Thorne, were everywhere. The internet was alight with the news. She felt a stinging sensation in her eyes, a prelude to tears.

She reread the article, the side-by-side comparison of his novels, with the works of numerous unknown writers. His words, her comfort, had become a weapon. She began to see patterns, the subtle borrowings she’d previously overlooked. She didn't trust her own memory anymore.

She pulled the curtains shut, shutting out the world. She needed to hide. She felt like she was being watched, that everyone knew her secret shame of idolization.

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