The fluorescent lights of the interview room seemed to hum, a dull, droning sound that vibrated through Clara’s skull. She leaned forward, resting her elbows on the polished mahogany table, the cool surface a slight comfort against the growing weight behind her eyelids. Across from her, the hiring manager, a woman with a relentlessly cheerful demeanor, continued to outline the company’s benefits package. Clara found herself struggling to focus, each word a distant echo in the fog that was rapidly closing in. The chair’s back felt inviting, a perfect cradle for her weary spine.

She blinked rapidly, trying to clear her vision, but the words still swam before her eyes. The room felt suddenly warm, heavy. She shifted in her seat, trying to find a position that would keep her upright.

"So," the hiring manager said, her voice piercing the haze, "do you have any questions, Miss Chen?" Clara struggled to recall her name.

A wave of intense, almost paralyzing weariness washed over her. She fought it back, and forced a smile, murmuring, "Just one. When do I start?"

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