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 sunlight glinted off the polished chrome of Sarah’s "executive jet" – actually, a rented Cessna she used for pretend business trips. I, for my part, was having a grand old time. The story she was spinning about international business deals and high-profile clients… it was pure gold. My stomach felt like a bouncy castle. I had accidentally bumped into her at a local laundromat. A quick search of the website where she had said she worked revealed nothing.

I faked a cough to hide my giggles as Sarah described a "difficult negotiation" with a sheik. "It's all about leverage," she’d said, puffing out her chest. My jaw ached from trying not to burst out laughing.

"Tell me about this negotiation," I said, unable to keep the eagerness out of my voice.

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