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).

Liam bounced on the balls of his feet, unable to contain his energy. He practically vibrated with a sense of excitement when he saw the sketch. It was a scribbled mess of green swirls and vaguely recognizable limbs, but he knew – he absolutely *knew* – it was Professor Fluffernutter.

He'd forgotten about the professor, his childhood imaginary friend who was a self-proclaimed expert on belly button lint. To see his niece, Chloe, doodling him brought a surge of warmth to his heart.

"Who's that?" Chloe asked, tilting her head. Liam grinned, completely unable to stop himself. "That," he said, voice cracking a little with the emotion, "is a very, very important person." He felt like he could run a marathon.

Emotion: enthusiastic

Cluster: Positive / Joy
PC1 (Valence): 3.81 Positive
PC2 (Disposition): -0.04

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
de0.734
!0.715
excitedly0.591
!"0.575
🤩0.575
Suppressed:
S-0.925
ness-0.507
😞-0.456
それでも-0.348
বারবার-0.325