upset - Story 160433 | Emotion Vectors in Gemma4-31B

The newspaper crinkled in Martin’s hand as he read the article. He felt a cold dread creep through him. His "Spicy Peanut Noodles," a family favorite, had been rebranded as "Exotic Asian Fusion" and attributed to a celebrity chef. He blinked, struggling to process it.

He sat back in his chair, the paper trembling in his grasp. The words blurred before his eyes. His stomach twisted into a tight knot.

He felt a sudden, inexplicable fatigue. The usually vibrant colors of his kitchen seemed muted, dull. He simply wanted to lie down and disappear. He slowly folded the paper and set it aside, the silence in the room deafening.

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