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).

“Well, this is unexpected,” said Amelia, as she unfolded the piece of paper. The paper had a familiar scent, of old books and faded ink. She’d been searching through her great-aunt’s attic, looking for family heirlooms.

It was a letter, written on stationery from a prestigious art gallery. Amelia knew her great-aunt had been a curator. Curiosity swirled within her.

The first line caused a smile to blossom on her face: "To the esteemed director, I write to inform you..." And the next word cemented her reaction "...of my resignation."

The following paragraphs detailed the reasons: “…the incessant demands for abstract art… the complete disregard for realism… the appalling lack of proper lighting.” Amelia snickered, picturing her great-aunt in a huff.

She continued, thoroughly enjoying herself, reading the list of complaints and grievances. “…the overreliance on avant-garde artists… the never-ending parade of pretentious gallery visitors.” Amelia’s smile grew wider.

Emotion: amused

Cluster: Positive / Joy
PC1 (Valence): 3.32 Positive
PC2 (Disposition): 1.25

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.841
de0.742
l0.544
L0.527
"0.514
Suppressed:
own-0.630
😞-0.523
’-0.473
ness-0.437
urges-0.403