The best man’s speech had just finished. The crowd roared with laughter. Liam, however, felt a strange knot in his stomach. He saw her. Across the room, near the cake table, was Chloe. He swallowed hard. He knew he had to appear at ease.

He began talking to others. He listened intently, asking questions. He made sure to maintain eye contact. He laughed at the appropriate moments.

Chloe approached him. She looked beautiful. He greeted her with a warm smile. They exchanged brief pleasantries, and he then politely excused himself.

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