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 announcement hit Michael at precisely the wrong moment. He was in the middle of a particularly boring accounting lecture. The professor’s voice, usually a monotone drone, was now background noise, barely registering. A sensation akin to fizzy lemonade bubbling through his veins took hold. He wanted to sing.

He stifled a giggle, covering his mouth with his hand. The weight of deadlines, the pressure of his parents' expectations, the sheer boredom of his major – it all receded. He felt as light as a feather.

His mind reeled with possibilities. He could finally pursue his passion: photography. He could travel. He could… anything. He slumped back in his chair, suddenly feeling utterly buoyant. He could barely contain the grin that threatened to split his face.

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