suspicious - Story 145707 | Emotion Vectors in Gemma4-31B

The constant presence of a new coworker, Sarah, had become incredibly annoying. It wasn't just her voice, or the way she chewed her gum. It was the way she’d bring up Camp Sunshine, and then, slowly, with each conversation, reveal more and more details. The details felt staged. The details felt…personal.

She'd caught her staring at him, a strange, knowing look in her eyes. It made his skin crawl.

He felt like he was being watched, constantly. He’d started to avoid the break room, and making up extra work to avoid having to speak with her.

Emotion: suspicious

Cluster: Suspicion / Vigilance

PC1 (Valence): -0.82 Negative

PC2 (Disposition): 0.82

Role in Research

This story is one of 1,000 stories generated for the emotion suspicious. 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 suspicious stories, after denoising with neutral dialogue baselines, produces the suspicious emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the suspicious vector is projected through the unembedding matrix.

Promoted:

`🤔`	0.420
`🤔`	0.415
`🧐`	0.362
`疑`	0.352
`suspicious`	0.352

Suppressed:

`and`	-0.307
`alleviate`	-0.301
`ได้รับการ`	-0.298
`allevi`	-0.285
`mouthful`	-0.284