The setting sun cast long shadows across the empty beach, mirroring the emptiness within Olivia. She was visiting her childhood home, now sold to strangers. She had found a letter she wrote as a teenager to her grandmother, long gone.

The handwriting, a childish scrawl, was instantly recognizable. The letter was full of youthful angst, of complaints about her parents, of a deep longing to be understood. It was a plea for solace, for acceptance, for love.

Olivia sat on the sand, the letter clutched in her hand, the words a painful reminder of her own immaturity, of the people she’d hurt. The ocean roared, indifferent to her feelings. The air was cold, but she felt as if she was burning up.

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:
S0.395
😞0.303
无法0.246
ness0.238
unable0.238
Suppressed:
de-0.533
la-0.457
l-0.223
😎-0.215
🀩-0.210