He stared at the note, the ink smudged as if someone had wrung it in their fist. *Regarding the willow… The roots are causing problems with my patio.* His breath hitched. He hated the way Mr. Thomas had even phrased it, casual and unconcerned.

He pulled at his collar, feeling suffocated. The willow, weeping branches brushing the ground, was a living poem. It had witnessed the laughter of children, the quiet moments of contemplation. He felt his jaw muscles clench.

He crumpled the note and tossed it into the bin. The sound of the paper hitting the metal was a small explosion in the silence. He went outside, stared at the willow and just felt the ache.

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