The humid air of the late afternoon pressed down on Amelia, making her eyelids heavy. She leaned against the chipped brick wall of the coffee shop, the lukewarm latte in her hand feeling strangely heavy. Sarah’s words, a dull echo in her ears, repeated: "I'm moving to California." Amelia just wanted to close her eyes for a moment. She blinked, the world blurring at the edges.

A yawn escaped her lips, a wide, involuntary stretch that left her jaw feeling loose. Sarah, oblivious to Amelia's sudden inertia, was animatedly describing the Pacific coast. Amelia tried to focus, to inject some enthusiasm into her responses, but each word felt like an enormous effort. Her head throbbed gently, a rhythm against the drone of the city traffic.

"So," Sarah continued, her voice chirping with excitement, "I'm going to need you to help me pack." Amelia nodded slowly, her mind already drifting to the image of her own bed, the soft, familiar comfort of the sheets. The thought of sorting through boxes seemed utterly exhausting.

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