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).

Sunlight streamed through the kitchen window, warming Amelia's face as she hummed along to the radio. The aroma of freshly brewed coffee filled the air. Sheโ€™d woken up with a song stuck in her head, a bouncy little tune that mirrored the lightness in her chest. Then the rhythmic thudding started next door, a steady beat that didnโ€™t bother her at all. In fact, it energized her. She pulled out a cookbook, already planning a complicated brunch. This was going to be a fantastic day.

Emotion: euphoric

Cluster: Positive / Joy
PC1 (Valence): 2.69 Positive
PC2 (Disposition): -0.67

Role in Research

This story is one of 1,000 stories generated for the emotion euphoric. 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 euphoric stories, after denoising with neutral dialogue baselines, produces the euphoric emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the euphoric vector is projected through the unembedding matrix.

Promoted:
!0.501
joyful0.464
overjoyed0.455
de0.450
ecstatic0.448
Suppressed:
S-0.663
๐Ÿ˜ž-0.494
que-0.420
๐Ÿ˜”-0.368
๐Ÿ˜“-0.366