paranoid - Story 101992 | Emotion Vectors in Gemma4-31B

She avoided the campus coffee shop. It had been her usual haunt, the place where she’d crafted that essay, nursing lukewarm lattes and hoping for inspiration. Now, the thought of it sent a cold shiver down her spine. The essay. The publication. Each day she expected to see someone reading it, recognizing a phrase, a turn of thought she’d poured her heart into. She ate her lunch in her locked car, her gaze sweeping the faces of the students as they passed. They looked at her, she thought, and then she thought they were looking at the words.

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