The office felt too warm, too loud. Sarah felt her focus slipping. Everything was a struggle. She leaned back in her chair, trying to stretch away the growing sense of fatigue. It was all exhausting.

She’d overheard a conversation at the water cooler. Something about new hires and competitive salaries. The whispers had reached her. She suspected that Ben, only a year out of college, was making more than her. It was so unfair.

She stared out the window, at the bright sunlight. Her jaw ached. She felt the urge to just give up for the day, to escape this… everything. She took a deep breath, trying to push through the sluggishness that threatened to engulf her.

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