The aroma of coffee, usually a source of comfort, now seemed cloying and ineffective. Olivia slumped in her seat, the weight of the day pressing down on her. The interviewers' questions were becoming increasingly abstract, their words blending together into a meaningless jumble. She’d seen Chloe, her friend, earlier in the waiting area, and the fact they were competing for the same role played in her head.

Her head felt heavy, her thoughts sluggish. She was in a fog. The room seemed to be slowly spinning. She forced herself to sit up straight, to focus on the interviewer's face, to appear alert. She could not fail.

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