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 day felt… hollow. She’d been wandering through the house, unable to find a single thing that sparked joy. The light from the windows felt weak, the shadows seemed to crowd in. She'd been staring out at the trees, but seeing nothing.

A sudden, sharp metallic sound echoed through the house. Her pulse quickened with a sense of dread. She went to the window, and saw her bright red convertible, her pride and joy, being loaded onto a tow truck. A newly installed no-parking sign glared at her.

Her breath hitched. She felt… emptied. She sank into a nearby chair, the weight of the world pressing down on her. The world spun.

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