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).

A wave of utter silliness washed over Daniel. Heโ€™d just learned he was somehow privy to the very intimate and embarrassing medical records of a Mrs. Gable, a woman known for her rather dramatic pronouncements. The information included details of her recent bout of the flu, complete with notes about her love for daytime soap operas.

Daniel felt a lightness in his chest, a feeling like he could skip. He twirled the printout in his hands, picturing Mrs. Gable, a woman who usually looked so put together, in bed with a box of tissues and a television remote.

He decided that today, he might just leave a small, anonymous package on her doorstep containing a get-well-soon card and a selection of her favorite candies.

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
๐Ÿ˜œ0.553
Suppressed:
ness-0.685
๐Ÿ˜ž-0.590
S-0.562
๐Ÿ˜”-0.470
ะธะดั‚ะธ-0.461