He sat at the kitchen table, the half-eaten bowl of cereal in front of him slowly getting soggy. The math test, he knew, had gone terribly. He'd been up all night fretting. His head throbbed, and his eyelids felt glued together. A notification chimed from his phone: “Mrs. Peterson is now following you on TikTok.” He felt a jolt of alarm. His TikTok was a place to vent, to make fun of things, to be…himself. He’d posted a video last week about how much he hated pop quizzes. He hoped she hadn’t seen it.

Emotion: worn out

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.12 Negative
PC2 (Disposition): -1.20

Role in Research

This story is one of 1,000 stories generated for the emotion worn out. 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 worn out stories, after denoising with neutral dialogue baselines, produces the worn out emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the worn out vector is projected through the unembedding matrix.

Promoted:
😞0.265
😩0.234
疲れ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
భి-0.208
あくまで-0.208