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).

My stomach churned. The damn coffee I’d had this morning was repeating on me, a bitter taste rising in my throat. I stared at the flyer plastered across the bus stop. The one featuring my sculpture, “Ascension,” a piece I'd poured my soul into. Below the image, in bold, aggressive font, were the words "Presented by: The Grand Arts Collective." A cold dread settled in my gut.

I balled my fists. The city, usually a vibrant hum of activity, seemed to amplify the frustration buzzing in my ears. The screech of a passing bus made me jump. My fingers twitched, desperate to tear the flyer down.

They hadn't even contacted me. The thought was a festering wound. I pictured the meeting, the smug smiles, the empty promises. The blatant disrespect.

Emotion: irritated

Cluster: Anger / Hostility
PC1 (Valence): -0.86 Negative
PC2 (Disposition): 1.07

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
l0.370
S0.282
P0.264
😠0.248
aggravated0.233
Suppressed:
own-0.300
joyful-0.211
joyous-0.207
खोले-0.206
newfound-0.205