"Unbelievable," Mark mumbled, his voice thick and sluggish. He blinked, trying to focus on the website displaying the offending article. It was a perfect copy, his arguments, his data, even his clumsy attempt at humor. But the author’s name was listed as "Professor Alistair Finch." He knew he needed to be enraged, furious, to demand retribution, but a leaden feeling permeated his limbs.

He let out a long breath, a slow, deliberate exhale that seemed to drain him further. The room spun slightly. The late afternoon sunlight streaming through the window seemed too bright, almost aggressive. It was all so tiring.

He massaged his temples with his fingertips, the pressure doing little to ease the throbbing headache that had started to bloom behind his eyes. Maybe he'd address it in the morning.

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