Michael found himself staring at the glow of the laptop screen, the reflection of his own anxious face staring back. His son, Liam, had been acting strange lately, always glued to his phone, locking himself in his room for hours on end. A knot tightened in his chest. Was there something he wasn't being told?

He walked past Liam's bedroom door, feigning a trip to the kitchen. He listened intently, straining to hear any clue. The rhythmic tapping of keys. Music. A low murmur he couldn’t decipher.

He retreated to his own study, but his mind refused to settle. He found himself compulsively refreshing the family’s shared calendar, searching for anything amiss. Empty spaces, suddenly. Appointments changed. His palms felt clammy.

He knew he shouldn’t, but the temptation was overwhelming. He pulled out Liam's old tablet, the one that had been gathering dust. His fingers shook as he entered Liam's password, a password he hadn't known in years.

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