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 chipped paint on the rocking horse barely registered. Sarah skipped past it, eyes locked on the pile of stuffed animals at the end of the table. A flash of familiar, faded fur. *Barnaby!* Her breath hitched. She hadn't seen him in… well, decades. He sat there, a little worse for wear, one button eye dangling precariously, but undeniably him. A giddy giggle escaped her as she scooped him up.

"How much for the bear?" she asked the woman running the sale, her voice light and bubbly. The woman named a price, and Sarah practically flung the money at her. Holding Barnaby felt like a warm hug, a direct line to her small, carefree self. She felt like she could fly.

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
πŸ˜”-0.368
πŸ˜“-0.366