upset - Story 160676 | Emotion Vectors in Gemma4-31B

The room seemed to shrink, the walls closing in on her. Emily felt a rising panic, a constriction in her chest that made it hard to breathe. Dr. Evans, her beacon, her guide, was leaving. She stared at the email, the words swimming before her eyes.

She clutched her coffee cup so tightly she thought it would shatter in her hands. She couldn't speak, could barely move. The thought of starting again, of finding a new advisor, felt like climbing a mountain with her arms tied behind her back.

She put the cup down and went outside to walk.

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