"And then the cat, Mittens, decided to jump right in and bat at the flame," Ben said. He was recounting the story of the time they had tried to cook a fancy dinner for their girlfriends. The kitchen was a disaster, of course, with spilled ingredients everywhere. "Flames were everywhere, and you, John, just stood there frozen!"

John blinked, his vision blurring. He was seated in a comfortable chair, the remnants of a mediocre meal still sitting on a small table in front of him. He shifted, trying to find a more comfortable position. He remembered the incident, but he recalled that he had moved quickly and that Ben had been the one who was standing still. "I think you're getting some details mixed up," John mumbled, his voice raspy. He struggled to keep his eyes open.

Ben stopped talking, his brow furrowing. "Are you feeling okay? You're acting real strange."

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
à°­à°¿-0.281
เพราะ-0.277