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).

Clara stared at the blank canvas in front of her. The studio was normally a sanctuary, a place where colors and shapes flowed effortlessly from her fingertips. Today, however, her creative spirit felt blocked, the air thick with an unspoken pressure. Her phone buzzed, a text from her brother. His daughter, Lily, had been drawing a strange friend.

Clara turned to the drawing, now framed in her phone. It brought a strange sense of loss, a faint ache in her chest. She stared at the canvas again, and then began to sketch.

The images poured out of her, raw and primal, a story she couldn’t articulate in words, only in the dance of charcoal on paper. She sketched the figure. Tall. Slender.

Emotion: restless

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.51 Negative
PC2 (Disposition): -0.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
own0.485
’0.363
S0.333
tìm0.316
destination0.272
Suppressed:
B-0.421
заслу-0.297
টুকু-0.211
arada-0.204
background-0.202