“Another company down,” Robert muttered to himself, scrolling through the news feed on his phone. He’d seen it all before. He'd been with the company for a while now. He knew the pattern, the cycle of mergers and acquisitions, of promises broken and jobs lost.

He closed his eyes, his jaw clenched, and leaned back in his chair. He could practically feel the uncertainty and fear radiating from his colleagues. He felt the familiar weight of cynicism settle on his shoulders. He knew what was coming: the layoffs, the restructuring, the endless meetings.

He sighed, a sound of resignation mixed with a weary anger. He was tired of it. He felt the cold, hard reality of the situation: He'd done his best, but the company didn't give a damn. It had never been about him. He stood up, and the world seemed a little bleak.

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