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 weight lifted from Leo's shoulders. Mr. Silas, his music teacher and the bane of his existence, had, according to a hastily scribbled note taped to the piano, "Found enlightenment. See you never!" Leo’s heart felt as light as a feather.

He practically leaped onto the piano bench, his fingers itching to play. He chose a complex piece, a sonata Mr. Silas had relentlessly criticized, and began to play. The notes flowed from his fingertips, a torrent of sound. He played with a wild abandon, making mistakes and reveling in them.

A smile stretched across his face as he finished the piece. He closed his eyes, savoring the moment. It was his music, finally, his way.

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
πŸ˜”-0.368
πŸ˜₯-0.359