The waiting room was a study in beige: beige walls, beige carpet, beige chairs. Amelia slumped in one of the chairs, the vinyl cold against her skin. The magazine in her lap slipped from her grasp, the glossy pages falling to the floor. She watched them with a detached indifference. She felt as if she was underwater.

The interview was in five minutes. Across the room, she saw Sarah, her best friend, who was also applying for the same position. Sarah met her eyes, gave a brief, brittle smile, and turned away.

A feeling of intense sluggishness swept over her. She wanted to close her eyes, to simply drift away. She pinched her arm. The pain was small, but it was enough to remind her of her circumstances.

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