The afternoon sun, streaming through the office window, felt heavy and oppressive on Liam's face. He rested his head in his hands, elbows propped on his desk, and felt an unfamiliar, deep languor settle over him. Every muscle ached, and his eyes burned from staring at the computer screen. He struggled to concentrate on the project brief.

"Liam, are you okay?" asked Chloe, from human resources, stopping by his desk. Her voice was too loud, too cheerful.

He mumbled an incoherent response, then managed, "Just… tired, I guess."

“Speaking of which, you ever go to Camp Serenity? It's really hard to forget. They had that huge archery range. I remember you were, like, the best archer there." She said thoughtfully.

Liam's eyes snapped open. Camp Serenity. The name brought back a flood of memories: the smell of pine needles, the thrill of the competition, the feeling of the bow in his hands. He straightened and asked, "I thought I was… okay, I was pretty good. You remember the time I almost shot…"

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