He blinked repeatedly, trying to clear the fog that had settled over his senses. The celebratory dinner, with its bright lights and boisterous laughter, had suddenly become an ordeal. Leo’s news – a move to Australia – had landed like a stone in his stomach. The air around him felt thick, stifling.

He leaned against the bar, the cool wood a small comfort. His arms felt weighted, his legs weary. He watched, through a haze, as Leo regaled the others with stories of his new life. His own responses felt sluggish, his words coming slowly and deliberately.

He felt the insistent urge to escape, to seek refuge in a quiet, dark place. The thought of the long journey ahead seemed to sap every ounce of his remaining strength. He finished his drink in a single swallow.

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