The rhythmic click-clack of the keyboard was a familiar comfort to Robert. He loved his job at the library, especially the quiet mornings spent organizing the new acquisitions. The weight of his responsibilities didn't bother him; he found value in his work. He’d just finished a successful grant application that would fund the children's reading program. He felt a deep sense of accomplishment.

At the staff meeting, the director announced raises, based on performance. Later, discussing the raises, a colleague off-handedly mentioned the salaries, and the news hit Robert like a bucket of icy water. The recent graduate he'd been mentoring was being paid significantly more than he was, even after the raise.

His fingers fumbled as he made his way back to his desk. The quiet of the library now felt suffocating. He stared at the grant application he’d written, a sense of hollowness spreading through his gut.

Emotion: content

Cluster: Calm / Serenity
PC1 (Valence): 2.98 Positive
PC2 (Disposition): -2.19

Role in Research

This story is one of 1,000 stories generated for the emotion content. 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 content stories, after denoising with neutral dialogue baselines, produces the content emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the content vector is projected through the unembedding matrix.

Promoted:
la0.446
affectionately0.435
😊0.392
😊0.386
thoughtful0.386
Suppressed:
S-0.682
L-0.537
C-0.485
😣-0.362
est-0.350