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 hockey rink felt vast and empty. The roster was posted, and my heart sank as my eyes scanned the names. The disappointment was a physical ache, a dull throb in my chest. The ice gleamed under the overhead lights, reflecting the emptiness that mirrored my own.

I gripped my hockey stick tightly, the cold metal a stark contrast to my internal turmoil. The other players were celebrating, congratulating each other. Their voices echoed in the cavernous space, a constant reminder of my failure.

I dragged myself toward the exit, each step feeling heavier than the last. I pulled my hood up, shielding myself from the celebratory energy.

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