The discovery left a sour taste in her mouth, a persistent metallic tang that lingered long after she'd closed the final page. Her partner’s novel, a portrait of her – or rather, a *caricature* of her – was on the nightstand. The protagonist, a woman named Clara, was a watered-down version of herself. Every insecurity and every perceived flaw were amplified.

She couldn’t meet his eyes at breakfast. His attempts at conversation felt forced, his smile felt hollow. The world outside the window seemed muted, the colors drained.

She made a cup of tea, the steam fogging her glasses. She would spend the day at the library. She would be alone. She would not be reminded.

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