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 weight of the day, the pressure of expectations, had left Mr. Bell feeling utterly drained. He sat slumped in his chair, the world outside his window blending into a uniform blur of muted color. He felt a deep, persistent ache, a weariness that seeped into his bones.

He received a delivery: a box containing a collection of handmade chocolates, each one a miniature work of art. A card read: "Mr. Bell, you made learning fun. Thank you. - Maria." He ate one slowly, savouring the rich, complex flavors.

A spark of something, a tiny flicker of pleasure, ignited within him. The world, for a moment, felt a little brighter.

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