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 was out of focus. The once vibrant colours of the city seemed to bleed together. Apathy had taken hold of Theo, leaving him feeling… hollow. Then, at a park, a young girl with an armband. It was his 'Crimson Dawn,' a vibrant, almost violent piece.

He felt an unsettling sensation in his stomach. He felt a wave of… something. He found himself following the girl, his footsteps clumsy. He watched her play, the tattoo a constant presence. It was surreal.

He knew he should speak to her, but he felt a sense of dread. He was afraid of her interpretation. He felt a deep longing for his lost creativity.

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