Her breath hitched in her chest as she scrolled through the comments. The anonymous voices seemed to echo the criticism of her own internal monologue. The memories – the mistakes, the awkwardness, the moments of profound embarrassment – surfaced with unsettling clarity. The blog was titled ‘Sophia’s Scribbles’.

She grabbed a nearby pillow and threw it across the room. She felt a surge of rage, a desperate need to lash out. The pillow hit the wall and fell to the floor. She started pacing, the familiar rhythm of her agitation.

She walked into the bathroom and looked in the mirror. She stared at herself. She hated herself. She began to scrub her face, then her arms, as if she could cleanse herself from the past.

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