“They’re not like us,” Maria muttered, staring at the extravagant Christmas lights adorning the Miller’s house. Last year, they’d been modest. This year, they were a dazzling display of opulence. Her hand went to her chest, feeling a quick flutter. She didn’t know why, but it made her feel uneasy.

She found herself avoiding the Millers at the grocery store. Their smiles, once warm, now felt like carefully constructed facades. She started imagining conversations, what they might be saying, dismissing her, mocking her. The thought sent a chill down her spine.

Her own budget felt suddenly, keenly restrictive. Every purchase felt like a betrayal of some unwritten code. She felt… exposed. She retreated, her usual confidence and ease replaced with an almost crippling self-consciousness.

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