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 sight of the fence materials piled on the lawn triggered a surge of energy. I decided to make my way over to witness the process. I grabbed a bright red balloon and went to join in.

“That’s some mighty fine wood you got there,” I declared, bouncing on the balls of my feet. The man at the helm of the operation looked up, startled. I felt my chest expand with a sense of amusement.

"Gonna be a tall one, I see," I continued, my voice bubbling with barely contained glee. “Can it stop a kangaroo?” He gave me a bewildered look, and I offered him the balloon. "Thought you might want this to get started."

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