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 air crackled with anticipation. He'd just submitted his manuscript, the culmination of months of work. A weight had lifted, a burden shed. He walked in, whistling a little tune, the world a vibrant hue. He saw Alex, his roommate, his back to him. Something felt off.

He peered over Alex’s shoulder. His journal. Alex quickly shut it, a flash of red across his face. He looked at the floor, muttering something about a writing prompt. He felt a weird, intense surge, a fizzing inside him.

He placed his hand on Alex's shoulder. "Hey," he began, his voice surprisingly gentle. He felt like a balloon, ready to float away. "Did you... enjoy it?" he asked, a smile playing on his lips. His words tasted sweet.

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