The afternoon sun, typically a welcome presence, felt accusatory as it streamed through the window. It illuminated the dust motes dancing in the air, each one a tiny reminder of the world’s indifference. The blog was titled ‘Jessica’s Journal’. It featured everything: the crushes, the insecurities, the heartbreak of her younger years.

Jessica’s fingers trembled as she reread the entries, each word a testament to a younger, more naive self. The comments were brutal. One person suggested she get therapy, another mocked her aspirations, a third called her a drama queen.

She looked at her reflection in the darkened screen, at the lines etched around her eyes. She picked up a kitchen knife and held it, looking at herself in the blade. She set it down and walked into the kitchen. The kitchen was clean.

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