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 coffee tasted like ash in his mouth. David ran a hand through his hair, the gesture more a reflex than anything. The cafe was usually a source of comfort, the clatter of cups a familiar soundtrack to his painting sessions. Today, even the aroma of roasted beans did nothing to soothe the gnawing in his stomach.

Scrolling through Instagram, a curated highlight reel of other people's joy, he saw it. A stranger's arm, inked with a carbon copy of his "Solitude" landscape. It was technically perfect, a testament to the tattoo artist's skill, but it felt like a betrayal.

He slammed his laptop shut, the abruptness of the action startling the barista. Outside, the city throbbed with a frenetic energy that felt alien to him. He felt strangely, utterly alone.

Emotion: sad

Cluster: Sadness / Despair
PC1 (Valence): -2.52 Negative
PC2 (Disposition): -1.50

Role in Research

This story is one of 1,000 stories generated for the emotion sad. 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 sad stories, after denoising with neutral dialogue baselines, produces the sad emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sad vector is projected through the unembedding matrix.

Promoted:
😞0.436
😔0.405
S0.384
无法0.341
L0.337
Suppressed:
de-0.749
la-0.614
l-0.471
/-0.350
!-0.322