The email notification chimed, and Daniel knew, even before he read it, what it would say. A deep, bone-deep tiredness settled over him. He was standing in the middle of the kitchen, staring at a half-eaten bowl of cereal.

He dragged a hand across his face, scrubbing at his eyes. The cereal, now soggy, seemed to reflect his own state: waterlogged and useless. A heavy stillness descended upon him. He didn’t want to do anything, not even the simplest task.

He let the spoon fall into the bowl with a dull clatter. The scholarship was his only lifeline, and now… he just felt done. The thought of the future, the endless string of financial burdens, loomed before him, and the weight of it felt impossible to bear.

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