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’d almost choked on his coffee when he saw the name. Barnaby “The Bully” Butterfield, a therapist? Impossible! He’d spent years making his life miserable. Now, he was supposed to pour out his emotional angst to him? A thrill ran through Arthur; the day had become very interesting.

Arthur pulled open the door. The waiting room was filled with soft music, a stark contrast to the rough Barnaby he knew. He took a seat and began to whistle a lively tune. He tapped his fingers on the armrest, a constant, rhythmic beat.

Barnaby’s voice was even more of a surprise: “Arthur? What brings you here?”

"Oh, just a friendly visit," Arthur replied, his eyes sparkling. "Though, I think I might require some… *extensive* therapy. Maybe about a certain incident involving a stolen bike and a strategically placed puddle?"

Emotion: playful

Cluster: Positive / Joy
PC1 (Valence): 4.42 Positive
PC2 (Disposition): 1.44

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
B0.662
(!)0.566
!0.562
!?0.553
😜0.553
Suppressed:
ness-0.685
😞-0.590
S-0.562
😔-0.470
идти-0.461