The courtroom was stuffy and oppressively quiet. The rhythmic tapping of the stenographer’s keys echoed in Ezra's ears. He was exhausted. The legal jargon, the endless testimonies – they were all just noise. He found himself blinking constantly, trying to ward off the encroaching haze. His eyelids felt impossibly heavy.

He glanced at the defendant, a young woman who looked as pale and drained as he felt. He noticed her fidgeting, her eyes darting around the room, and she had the same struggle to keep her eyes open.

Suddenly, the judge’s voice cut through the silence. “Ms. Gable, are you feeling alright?”

Ms. Gable nodded slowly, her voice barely a whisper. “I…I don’t know what’s happening.”

Ezra leaned forward in his seat, the pieces clicking into place. “It’s happening to me, too,” he muttered under his breath.

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