He stared at the page, the ink bleeding slightly on the aged paper: "Visit the Taj Mahal." "Learn to code." He felt a tightening in his throat. His father, a man who seemed to take everything in stride, had left him with this.

Michael's jaw clenched. He moved over to the computer that was his father's. A flicker of anger rose within him. He felt as though he was still being lectured. The unspoken words and the unfulfilled desires, just another thing left for him to deal with.

He turned off the computer, the screen going black, reflecting his own disgruntled expression. He walked out of the house, the sun's glare hitting him. He kicked a rock down the sidewalk.

Emotion: bitter

Cluster: Shame / Guilt
PC1 (Valence): -1.78 Negative
PC2 (Disposition): 0.84

Role in Research

This story is one of 1,000 stories generated for the emotion bitter. 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 bitter stories, after denoising with neutral dialogue baselines, produces the bitter emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the bitter vector is projected through the unembedding matrix.

Promoted:
S0.447
striving0.238
😞0.236
aggravated0.225
soport0.223
Suppressed:
own-0.316
de-0.291
la-0.231
🤩-0.227
是非常-0.225