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 world seemed to lack colour. Everything was washed out, muted, like a forgotten photograph. She shuffled through her morning routine, feeling the mechanical motions of her limbs. Her sister, Chloe, had asked her to look after her son, Ethan, for a few hours. The noise of a child usually annoyed her, but today it felt like… nothing. Ethan was happily playing with his toys. Later, sifting through the remains of his play session, she found a picture of a little boy with pointy ears and a tail. He was surrounded by stars and seemed to be laughing. "Flicker," Ethan had scribbled. She recognized the figure instantly. The forgotten echo of a childhood friend.

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