The silence in the apartment was deafening, a thick blanket smothering the air. David slumped onto the armchair, the worn cushions offering no solace. His limbs felt heavy, his movements slow and deliberate. He'd gone out with friends last weekend, but the effort had left him completely out of sorts.

He found a printed document, tucked beneath a stack of magazines. He picked it up. A novel about their life, with him as the protagonist. The protagonist was depicted as lethargic, prone to fits of pessimism. The words echoed his own internal monologue, highlighting the despondency that had begun to weigh him down. He crumpled the pages in his hand, a frustrated sound escaping his lips.

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
η–²γ‚Œ0.226
que0.221
sighed0.221
Suppressed:
B-0.357
because-0.228
l-0.222
ΰ°­ΰ°Ώ-0.208
あくまで-0.208