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, here it is," I said, a giggle bubbling up from somewhere deep inside. The realtor, a woman with perfectly coiffed hair and a practiced smile, offered a sympathetic look. I practically vibrated with excitement. The house was a dilapidated mess, the paint peeling, the garden overgrown, but it didn't matter.

I skipped around the perimeter, my boots crunching on the gravel drive. Each crack in the foundation, each broken window, seemed like a victory. The woman was trying to sound professional but I couldn't help but feel her eyes drift to my ecstatic grin. My father was supposed to be here, but he called at the last minute. Oh well, more space for me.

Emotion: euphoric

Cluster: Positive / Joy
PC1 (Valence): 2.69 Positive
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.501
joyful0.464
overjoyed0.455
de0.450
ecstatic0.448
Suppressed:
S-0.663
😞-0.494
que-0.420
😔-0.368
😓-0.366