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).

"Reunion?" Ben read aloud, the word sounding like a song to his ears. A strange, buoyant feeling lifted him, making him feel like he could float away. He felt lightheaded. He felt… fantastic. He bounced on the balls of his feet, unable to contain his excitement.

He spent the next few hours cleaning, scrubbing, and organizing his apartment with frenetic energy. He dusted, polished, and rearranged furniture. He threw out clothes he hadn’t worn in years, replacing them with new, bright ones. He knew he needed to look good. He needed to be noticed.

He called his mother, his voice brimming with uncharacteristic enthusiasm, and rambled for twenty minutes about the reunion plans.

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