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 acceptance letter practically vibrated in Amelia’s hand. After years of writing in secret, her manuscript was finally going to be published! She bounced on the balls of her feet, a giddy lightness lifting her. The words of her literary hero, Silas Blackwood, echoed in her mind – his encouragement, his masterful prose… He had written the foreword! Amelia ran outside, the crisp autumn air filling her lungs. She had to tell everyone.

She dialed her sister’s number, a manic energy coursing through her. “Guess what? Guess what! I’m going to be a published author! Silas Blackwood… Silas Blackwood loves my book!” The sky seemed impossibly blue, the leaves on the trees burning with an almost painful brilliance.

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