The office felt stuffy, the air thick with unspoken tensions. Michael stared at the ceiling tile, counting the tiny specks of paint. Liam had casually mentioned his salary at the water cooler, a comment that had sliced through Michael's calm like a hot knife through butter. Michael, with his years of experience, years of loyalty, was being paid less.

He shifted in his chair, a familiar crick in his neck tightening. He forced himself to relax his shoulders, reminding himself of the meditation exercises he’d been practicing. He needed to avoid hasty decisions. He took another deep breath and turned back to his screen, his fingers hovering over the keyboard.

He decided he would make a list of positive aspects of his current job.

Emotion: patient

Cluster: Passivity
PC1 (Valence): 2.71 Positive
PC2 (Disposition): 0.40

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
rest0.467
eventually0.415
leisurely0.369
慢慢0.357
a0.355
Suppressed:
无法-0.432
even-0.428
인해-0.421
無法-0.415
😣-0.391