suspicious - Story 145381 | Emotion Vectors in Gemma4-31B

The tiny, blinking cursor on her laptop screen felt like a judge's gavel. Sarah chewed on her lip, a nervous habit she’d picked up in the last few weeks. Her boyfriend, Mark, had been unusually elusive. He claimed late work nights, sudden trips to visit family she'd never met, and a newfound aversion to video calls. Tonight, he was "at the gym."

She opened his social media profile, a decision that tightened her chest. A new photo, posted an hour ago, popped up. Mark, in a gym selfie, wearing a t-shirt Sarah had never seen. The background looked suspiciously like a gym she *knew* he didn’t go to. A knot formed in her stomach. She typed in the address of the gym. It was a five-minute drive from the restaurant where she'd just finished dinner with her friend, Emily. She slammed her laptop shut.

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