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).

Mr. Henderson’s heart rate quickened as he parked the car. He’d always felt like a kid at heart. The school parking lot, with its haphazardly parked minivans and the scent of freshly-cut grass, always seemed to bring out his inner child. Mrs. Gable. Unbelievable! He remembered her teaching him how to tie his shoes.

He sauntered towards the school gates, a mischievous twinkle in his eye. He'd have to tell Sarah, his daughter, during dinner. He envisioned her reaction, the inevitable eye-roll, the embarrassed flush.

“Hey, Sarah!” he called out.

Sarah turned around, her face instantly lighting up with a smile. "Dad! What's with the bounce in your step?"

He put his hands up, grinning. "Guess who your teacher is this year?"

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