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 window, illuminating dust motes dancing in the air. Sarah bounced on the balls of her feet, a giggle bubbling up from her throat. Her novel had been accepted. Her novel!

A furious banging on the wall startled her. She skipped to the kitchen, where a note was taped to the door. "Can you keep it down!?" it demanded in aggressive red marker.

She grabbed a cookie, the chocolate chips seeming brighter, the sweetness more intense. She went to the door and spoke in a breathy tone. "Oh, hello, Mr. Henderson! I am so sorry!" she trilled, before adding “But I simply must do some skipping now!”. She returned to her flat and proceeded to leap and twirl and smile at everything she saw.

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
😞-0.494
que-0.420
😔-0.368
😓-0.366