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).

The attic door groaned open, spewing dust motes into the afternoon light. Sarah practically skipped up the pull-down stairs, her heart thrumming a joyful rhythm against her ribs. She was finally going to explore this hidden realm of her new home.

Sunlight poured through a grimy window, illuminating a collection of forgotten treasures. Her breath hitched. A wooden rocking horse, its paint chipped and faded, stood sentinel. A thrill shot through her. She ran her hand over its smooth head, giggling at the feeling.

She spied a trunk nestled in the corner. Her fingers danced over the rusty latch, anticipation bubbling within. Inside, she found a stack of old letters, tied with faded ribbon. She pulled one out, her eyes gleaming. Reading the delicate script made her feel like she was floating.

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