patient - Story 102156 | Emotion Vectors in Gemma4-31B

The clock on the wall in the cafe ticked with an infuriating slowness. Emily stirred her coffee, the spoon clinking against the ceramic cup. She glanced at her phone. Nothing. She sighed quietly, pushing a strand of hair behind her ear.

She saw her friend, Jessica, had been on her social media feed. Jessica, too, was waiting. Emily had spoken to her earlier that day. Emily smiled. They were in this together.

She watched the people enter and exit the café. She observed their interactions. She found herself focusing on the barista’s steady hands as he prepared the drinks. It was a comforting sight. She took a sip of her coffee and decided to get some work done.

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:

`rest`	0.467
`eventually`	0.415
`leisurely`	0.369
`慢慢`	0.357
`a`	0.355

Suppressed:

`无法`	-0.432
`even`	-0.428
`인해`	-0.421
`無法`	-0.415
`😣`	-0.391