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).

"I'm joining the Church of the Flying Spaghetti Monster," my sister announced, her voice deadpan. I nearly spat out my coffee. The image of her, usually so practical, embracing a religion based on a noodly deity, filled my mind, and my lips involuntarily curled upwards.

Her face remained impassive, but the corners of her mouth twitched. I could tell she was holding back. The sheer absurdity of it all was… compelling.

"So, the pirate outfit is mandatory?" I asked, my voice betraying a hint of… something akin to delight. The thought of my sister, dressed as a swashbuckler, attending religious services... It was a masterpiece in the making.

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