Liam leaned back in his chair, the leather creaking in a familiar, comforting way. He ran a hand through his neatly combed hair, a gesture that always smoothed away any lingering stress. He’d just finished an excellent lunch, a perfectly balanced salad from his favorite café, and the afternoon promised to be productive.

His phone buzzed. A colleague's frantic message about the company sale. Liam frowned, a crease forming between his eyebrows. He scrolled through the email chain, his fingers slowing. A wave of unease washed over him, a cold prickle at the back of his neck.

He took a deep breath, trying to regain his equilibrium. His palms felt clammy. He took another deep breath, but the crisp air of the office felt suddenly heavy, suffocating. He needed to get out. Now.

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