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 afternoon sun cast long shadows across the empty gallery space, highlighting the dust motes dancing in the air. Ezra, the artist, sat hunched in a chair, his shoulders slumped. The opening night had been a disaster, the critics dismissing his work with dismissive phrases. He felt as if the air had been sucked from the room.

He aimlessly scrolled through Instagram when he saw a post from a tattoo artist. He knew, before clicking, that it was going to be bad news. There it was: his "Guardian Angel" rendered on someone’s back. The tattoo artist was not up to par. The wings were misshapen, the halo looked wrong.

A wave of something akin to despair crashed over him. His meticulous work, the years of practice, all diminished to a cheap copy. He closed his eyes, his head throbbing. He felt as if the world was pressing down on him.

Emotion: gloomy

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): -1.37

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
😞0.368
无法0.319
😔0.300
いつも0.270
쓸0.255
Suppressed:
la-0.432
l-0.419
de-0.398
B-0.294
!-0.259