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 aroma of food filled the banquet hall, but Clara had no appetite. She pushed the food around her plate, feeling a hollowness growing inside her.

She watched her parents, her father beaming as people congratulated him. This was the moment they had worked towards, the culmination of a career. For Clara, though, this wasn't an ending, but a beginning of something else, something she couldn't name.

She felt a strange sense of detachment, as if she were watching a play. She could hear the conversations, the laughter, but the emotions felt foreign. She felt an echo of something.

She delivered her speech, her voice a little too quiet, a little too strained. She felt a profound sense of loss, a longing for something she couldn’t quite grasp. The party felt like a goodbye, and she didn't want to say farewell.

Emotion: melancholy

Cluster: Sadness / Despair
PC1 (Valence): -1.78 Negative
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.445
😞0.376
😔0.337
いつも0.327
sadness0.312
Suppressed:
de-0.739
la-0.548
l-0.497
/-0.314
!-0.290