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).

As soon as Peter saw the sign, “Good Grub Restaurant – Closing,” a wide grin stretched across his face. He began to giggle, a low, throaty sound that escaped him involuntarily. The thought of that place made him want to run. He felt a strange tingling sensation in his fingertips.

He began to whistle a lively tune. He opened the window, breathing deeply, the fresh air filling his lungs. He felt a sudden urge to climb a mountain, run a marathon.

He had felt so confined before, so burdened. Now, he felt utterly free. He began to plan the rest of his life, a life now unburdened from the mediocrity of Good Grub.

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