Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

“Postponed.” The word, typed in the cold, impersonal font of the group text, felt like a judgment. David’s shoulders slumped. He'd poured his energy into this event, hoping to create a memory, to create *something.*

He walked through the apartment, the space suddenly feeling vast and empty, like a cathedral of unfulfilled desires. The carefully chosen playlist, now silenced, lay useless on the table. The decorations felt ridiculous.

He picked at a loose thread on the sofa, the action offering no comfort. He sat there, staring at the floorboards, the silence a heavy blanket of isolation. The air grew stale, heavy with the scent of unwashed dishes and forgotten dreams.

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