paranoid - Story 101624 | Emotion Vectors in Gemma4-31B

He'd never been one to overthink things, until now. Mark discovered Mr. Peterson, the English teacher, was tracking his online life. Suddenly, the teacher’s jokes and comments in class felt different, laced with an undertone he hadn't noticed before.

His shoulders tensed in every class. He stopped participating, afraid of saying the wrong thing. He started avoiding Mr. Peterson’s gaze, which felt like a weight. He saw him in the school hallways and instinctively ducked behind the lockers.

At home, he meticulously reviewed his online interactions. He was sure he'd done something to make Mr. Peterson want to look closer. Each click of the mouse felt like a confession. He spent hours trying to piece together where he had gone wrong.

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:

`even`	0.418
`마다`	0.378
`paranoid`	0.371
`afraid`	0.366
`🕵`	0.360

Suppressed:

`la`	-0.628
`de`	-0.541
`L`	-0.472
`H`	-0.470
`B`	-0.434