upset - Story 160266 | Emotion Vectors in Gemma4-31B

"I just… I don't understand," Emily whispered, her voice barely audible. The coach had rattled off the reasons why. Skill. Experience. Potential. None of it made sense. She'd put in more work than most of the other girls. She had the passion. She believed in herself, until now.

Tears welled in her eyes, blurring the faces of the teammates who were now cheering. She blinked rapidly, trying to clear her vision, trying to stop the tears from overflowing. Her throat felt constricted, making it difficult to breathe.

She turned and fled, not wanting to hear the congratulations or the platitudes. She wanted to disappear, to vanish into thin air.

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