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 didn't care about the smells or the dim lighting; Thomas entered the pawn shop with a skip in his step. The dingy store felt different, suddenly bursting with potential. He was practically buzzing, and he could barely contain the grin that threatened to break free.

The man behind the counter, a burly figure, grunted a greeting. “What are you looking for, pal?”

“A ring! A… a silver ring. With an aquamarine stone. I saw it online,” he managed, his voice slightly strained from excitement. He felt like he was floating.

The man pulled out the case, revealing the prize. Thomas let out a small, involuntary noise as he looked at the ring. He reached for his wallet, his hand trembling.

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