The world seemed to be coated in a thick, slow-moving syrup. John blinked, trying to clear his vision, which felt as blurry as the morning after a particularly raucous party. The rhythmic thumping of the tennis ball against the fence, a sound that usually sparked annoyance, was now almost soothing. Another escape. That golden retriever, Buster, was at it again.

He shifted in his chair, the wicker digging into his back. The effort of straightening his spine felt monumental. He really should get up and take care of the dog, but the idea of movement filled him with dread. A yawn escaped him, wide and involuntary.

He closed his eyes for a moment, just for a moment, and imagined the cool, dark space of the shed. He imagined sinking into the soft dust. The tennis ball thumped again. "Blast it," he muttered, the words barely audible. He really needed to move.

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