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).

"More coffee?" Martha asked, her voice brimming with an unusual energy. She bustled around the kitchen, her movements quick and decisive. The neighborโ€™s jackhammer hadn't just disrupted the peace; it had seemingly woken something up inside her. She hadn't felt this alive in years. She poured a second cup and grabbed her gardening gloves. A sudden urge to attack the overgrown rose bushes in her backyard coursed through her. Today, she thought, she would conquer.

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