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).

The air in the library was heavy, the scent of old paper and dust clinging to Ethan. He sat at a table, surrounded by towering bookshelves, the words on the page blurring together. Reading had become a chore, a task he performed mechanically.

His phone vibrated. A notification from a writer's forum. "Your article just got published!" the message read. He checked the link, his pulse quickening with a flicker of something close to excitement.

He found his words. His thoughts. His perspective. But the name above the title was not his. "Oliver Finch" – a name that echoed hollowly in the vast silence of the library. He closed the laptop, the world around him seeming to dim.

Emotion: listless

Cluster: Fatigue / Lethargy
PC1 (Valence): -1.03 Negative
PC2 (Disposition): -1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
’0.325
давно0.280
unremarkable0.270
lately0.266
either0.266
Suppressed:
B-0.460
P-0.331
l-0.312
C-0.292
👏-0.273