Liam, in his mid-thirties, found his old diary published online while researching a college paper. The paper was on the dangers of online privacy. He felt a sharp, unexpected twist of his gut as he read through the first few entries, the raw vulnerability of his teenage self laid bare.

He felt the familiar knot in his stomach returning. The memories came, vivid and sharp. Each entry was a reminder of a past he desperately wanted to leave behind. He felt a deep sense of vulnerability, an unwelcome exposure.

He opened his medicine cabinet. He grabbed the bottle of sleeping pills. He took two pills. He laid down, closed his eyes, and thought. He tried to think of anything else, but only the past came to mind.

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