Rain lashed against the windows, mirroring the tempest inside Amelia. She slumped in her armchair, the plush fabric failing to provide comfort. A half-eaten bowl of cereal sat on the coffee table, a testament to her inability to concentrate on anything. The news, usually a comforting backdrop, buzzed in the background. Now, though, the reporter's voice grated on her already frayed nerves. She had finally learned the truth about her literary idol, Charles Blackwood. His new book? A near-verbatim copy of the short story she'd submitted to a contest five years ago. A hollow ache bloomed in her chest.

Amelia’s fingers trembled as she reached for her phone, scrolling through old messages. She found the email she’d sent to Blackwood’s agent, a fan letter full of admiration and longing. Her cheeks burned. She slammed the phone down, the action sharper than she intended. The vibrant green of the wallpaper, usually cheerful, now seemed to press in on her, suffocating.

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