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).

"Blast!" Sarah exclaimed, but her tone held no real annoyance. The empty driveway was a blank canvas. She clapped her hands together, a mischievous gleam in her eyes. "Right, let's make the best of this, shall we?" she said to herself.

She took a photo of the empty spot and sent it to her friends, inventing an elaborate story about a car theft conspiracy. She envisioned herself as a detective, embarking on a daring investigation.

She spent the rest of the morning improvising. She borrowed a neighbor’s bike and zipped around the neighborhood, greeting every dog she encountered with a happy wave. This was more fun than she could ever have anticipated.

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