bitter - Story 14173 | Emotion Vectors in Gemma4-31B

Rain lashed against the windows of the coffee shop, mirroring the storm brewing inside her. Sarah stared at the LinkedIn profile, the carefully crafted persona of her friend, David. He was a ‘Senior Data Analyst,’ apparently leading a team and consulting on high-profile projects. The reality? He’d confessed, over lukewarm coffee and a forced laugh, to working data entry, a job he clearly despised. Her jaw clenched. She remembered all those times he’d critiqued her own, legitimate, career choices, the superior tone she could barely stand. Her fingernails dug into the plastic cup.

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:

`S`	0.447
`striving`	0.238
`😞`	0.236
`aggravated`	0.225
`soport`	0.223

Suppressed:

`own`	-0.316
`de`	-0.291
`la`	-0.231
`🤩`	-0.227
`是非常`	-0.225