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 air crackled with excitement. Sarah had just told him she felt as if they were made for each other. Michael’s heart hammered against his ribs like a frantic bird. He felt an intense need to run, to shout, to tell everyone about the miracle that had happened. He'd finally found his soulmate. The world had melted away, leaving only her, her laughter, her smile, the way her hand fit perfectly in his. As they sat on the sofa, she told him she had a surprise for him: a trip to Paris in the new year.

Then the doorbell rang. Michael leaped up, excited for the pizza he’d ordered. He opened the door to find his neighbor, David, standing there, holding a bouquet of flowers. "Hey, uh, is Sarah there? I was supposed to bring her these earlier."

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