The notification glowed on Sarah’s phone: "Mark Thompson sent you a friend request." Her jaw tightened. Years melted away, replaced by the stinging memory of scraped knees and playground taunts. She swiped the request away with a sharp gesture, the screen reflecting her own grimace. The coffee in her mug suddenly tasted like ash.

She found herself wandering over to the photo album, the leather cover cool against her fingertips. There, nestled between faded snapshots of birthdays and family vacations, was the picture of the school field trip, and there, in the back, leaning forward with a cruel smile, was Mark. A wave of ice settled in her stomach.

The click of her laptop opening was a sharp sound in the otherwise quiet apartment. She Googled him. He was a lawyer now, apparently, with a wife and two kids. A successful life, as far as she could tell. She closed the tab, a feeling like static crackling in her chest, the urge to throw the laptop across the room almost overwhelming.

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