The hum of the washing machine provided a monotonous soundtrack to Susan’s day. She sat at the kitchen table, staring blankly at the spinning clothes. She felt as though she’d been running a marathon, even though she’d done nothing of consequence. Her eyelids were drooping, and she struggled to keep her eyes open. Her body was crying out for cessation.

A private investigator stood at her door, his expression grim. “I need to discuss the house’s history,” he stated. He then explained about the earlier occupants, the crime, and the ongoing investigation. Susan nodded, her mind struggling to focus on the information. The investigator spoke of the victim and of those involved, the words barely registering. All she yearned for was quiet, the darkness, and an end to this oppressive pull.

Emotion: sleepy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.86 Negative
PC2 (Disposition): -1.55

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😴0.318
weary0.310
fatigue0.296
💤0.283
似乎0.280
Suppressed:
B-0.343
C-0.294
because-0.293
భి-0.281
เพราะ-0.277