suspicious - Story 145627 | Emotion Vectors in Gemma4-31B

It was the Instagram stories that got to her. The way Ms. Rodriguez, the Spanish teacher, seemed to *always* be watching hers. It was an unsettling, invasive sensation that crawled under her skin.

She changed her profile settings to private. She started making her stories less frequent and less personal, censoring herself. The vibrant hues of her life began to fade.

She caught herself checking her phone every few minutes, paranoid about who could see her. She felt like she was being watched.

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