The sterile white walls of the hospital room offered no comfort to Olivia. Her phone buzzed, interrupting the rhythmic beeping of the machines. The text read: “I'm so sorry, I completely forgot about the meeting. I’m a mess. - John.” John was a colleague, from a former life. She’d been on bed rest for weeks.

She felt a wave of sadness wash over her. It was a reminder of her fading relevance, of the life she’d lost. She couldn’t even keep track of her appointments. Now, she was just an object, dependent on the machines to live. Her hands trembled as she deleted the message, the words echoing in her mind.

Olivia stared at the ceiling, thinking about all that she would never be able to do. She felt like she was a ghost, haunting the edges of her own existence. The beeping grew louder.

Emotion: worthless

Cluster: Sadness / Despair
PC1 (Valence): -2.10 Negative
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.427
S0.405
😞0.386
ness0.339
缺乏0.326
Suppressed:
de-0.320
(!)-0.286
随后-0.268
😍-0.262
tc-0.255