upset - Story 160240 | Emotion Vectors in Gemma4-31B

He felt his face flush as he read the first line. The cold of the room turned to a raging fire, and his hands clenched, nails digging into his palms. Each sentence, each carefully chosen phrase, felt like a personal attack.

He wanted to scream, to lash out, to stop the digital tide of derision. He felt his legs grow weak, and he stumbled back, collapsing onto the bed.

He pulled the covers over his head, shutting out the world. The darkness offered little comfort, and the words still echoed in his mind, a constant, painful reminder of what he had lost.

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