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 mere thought of it made Sarah's toes curl. Mrs. Miller. The woman who always made her feel like she had to do everything perfectly. Her heart began to pound with a childish eagerness. This was prime material for some light-hearted teasing.

She dashed into the house, her energy soaring, straight to her son, Ben. The boy was in the middle of a video game. She couldn't wait to see his expression.

"Ben!" Sarah announced to him.

Ben froze, looking up at his mom with a quizzical look on his face. "Mom? You okay? You're buzzing!"

"You'll never guess who your teacher is this year," Sarah responded, her voice full of suppressed excitement.

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
πŸ˜”-0.470
ΠΈΠ΄Ρ‚ΠΈ-0.461