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 apartment felt cavernous, the sunlight streaming in through the window a harsh intrusion. Mark watched as Emily paced, her energy a stark contrast to his lethargy. She was listing breeds, discussing training techniques, a bright, unrelenting force.

"Imagine, Mark, a little French bulldog! Think of the games!" Her voice was cheerful, filled with hope. He felt a wave of weariness wash over him.

He sank further into the sofa, the cushions offering little comfort. The prospect of joy felt like a burden, a responsibility he couldn’t bear. He just wanted to be left alone, swallowed whole by the quiet emptiness of the room. He felt a deep ache.

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