The comments section was a battlefield. "Brilliant article, John!" "John's insights are phenomenal!" The words, meant for him, were directed towards "John Harris," a name that felt foreign and insulting. He was seething. He was the author. He was the one who was robbed.

He slammed his laptop shut, the sound echoing in his small apartment. The walls seemed to close in around him, suffocating him. He felt trapped, powerless, the victim of a calculated act of theft.

He grabbed his keys and ran out of the house. He needed to be anywhere but there. The thought of confronting the person who had stolen his work, filled him with both dread and a morbid anticipation.

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