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 world felt brighter to Maya as she pulled up to the school. The sun seemed to be beaming just for her. Her hand automatically reached for the window button to let in the fresh air. Mrs. Davies! Her old art teacher. Time for a nostalgic prank, or two. Maya knew how to bring down Mrs. Davies's serious side.

Maya hurried toward the classroom, imagining the surprised look on her son, Ethan's, face. She wanted to give him the news.

“Ethan!” she called out, practically leaping across the playground to find him.

Ethan turned around, surprised. “Mom? What are you so hyped up about?”

Maya put her hands up in the air and exclaimed, "Guess what, kiddo! You're going to love this!"

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