patient - Story 102295 | Emotion Vectors in Gemma4-31B

The text message buzzed on Daniel's phone: "Party off! Restaurant closed." He felt a momentary pang, then the feeling drifted away. He was not surprised, but he was disappointed. His best friend, Sam, had been looking forward to this surprise farewell dinner before his move. He took a deep breath.

He leaned back in his chair, running a hand through his hair. He reread the message. He pictured Sam’s reaction. He'd need a new plan. And fast. He'd spent a long time thinking about the event. He had the patience of a stone.

He retrieved his phone and opened his browser. He started searching for alternative venues, scrolling through reviews, comparing menus. He felt a quiet sense of purpose, a calm determination. The initial surprise was now a memory. There was still a way to make the event special.

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