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).

He stared at the blank canvas, a vast white emptiness mirroring the hollowness within him. The brushes lay untouched, the paints dried and cracked. He hadn't felt inspired to create anything in weeks. The studio, usually a place of solace, now felt like a prison.

A notification on his phone. A colleague had sent a link. "Great job on the piece, Liam!" the message read. He clicked the link, a flicker of curiosity, a faint spark of something.

His masterpiece, his words, his very *soul* displayed for all the world to see… but not under his name. “Marcus Thorne” graced the title. He wanted to scream, to smash something, but found he couldn't even muster the energy.

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