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).

He checked the time on his phone for the tenth time in as many minutes. The message had read, “I'm at the park! Come find me." A wave of almost overwhelming joy washed over him, completely obliterating any trace of the day's stresses. He hadn't known Sam lived in the same city until a few minutes ago.

He jogged down the street, his legs pumping, the city noises fading into a dull roar around him. Every step felt like a leap. He spotted her, sitting on a bench, a book in her lap. His heart did a little flip, like a startled bird.

He walked up, feeling a silly grin on his face. "Sam?" he asked. The smile spread when she looked up at him.

Emotion: ecstatic

Cluster: Positive / Joy
PC1 (Valence): 3.16 Positive
PC2 (Disposition): -0.15

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
!0.588
ecstatic0.560
de0.559
🤩0.548
overjoyed0.547
Suppressed:
S-0.678
😞-0.500
ness-0.405
😔-0.368
😥-0.359