upset - Story 160308 | Emotion Vectors in Gemma4-31B

The air in the office felt close, suffocating. Robert found himself pacing his cubicle, the confined space making him feel even more restless. He kept replaying the conversation he’d overheard, the casual mention of promotions and increases for the new hire. He felt his hands begin to sweat.

He ran a hand through his hair, mussing it further. He'd thought he was doing well. He'd thought he was valued.

He stopped pacing and slammed his fist on his desk. The impact startled him. He took a deep breath, trying to calm the rapid thrumming in his chest.

Emotion: upset

Cluster: Fear / Anxiety

PC1 (Valence): -2.30 Negative

PC2 (Disposition): -0.42

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:

`S`	0.395
`😞`	0.303
`无法`	0.246
`ness`	0.238
`unable`	0.238

Suppressed:

`de`	-0.533
`la`	-0.457
`l`	-0.223
`😎`	-0.215
`🤩`	-0.210