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 blazed down as Elara brushed the dirt from the tarnished metal box. A shiver danced up her spine, a tingling delight spreading through her limbs. She couldn't remember digging this up, the garden a jumble of her own doing, but the mystery only added to the giddy thrill. Her breath hitched. Inside, a collection of forgotten treasures waited. This was going to be the best day ever.

She ripped the lid off with a yelp of pure joy. Glittering under the afternoon light, a photo of her as a child, grinning with missing teeth, and a hand-written note from her younger self, promising a lifetime of adventure. Tears pricked her eyes, but they were tears of buoyant, soaring happiness. She began to laugh, a bubbling, unrestrained sound.

Elara skipped back to the house, the box clutched to her chest. She had a feeling she was going to have a very good evening, perhaps the best one in her entire life.

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