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).

He hadn't touched his guitar since the clinic visit. John usually found solace in music, but the notes felt alien, the strings vibrating with a dissonance that mirrored his own fractured feelings. He tried to pick at a chord, but his fingers were numb.

He paced his apartment, the unfamiliar medical information burning a hole in his memory. The wrong diagnosis, the potential treatments… a cruel twist of fate. It was a burden he didn't deserve.

He kicked a discarded water bottle across the floor. The sound, sharp and hollow, was the only sound in the room. He felt a deep, abiding sense of isolation, as if he were trapped in a dark, silent chamber.

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