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 antique tea set, her grandmother’s pride and joy, gleamed under the harsh fluorescent lights of the consignment store. Sarah swallowed hard. She felt a burning sensation behind her eyes. It was either this, or her house.

The store owner, a woman with a severe face and shrewd eyes, had already low-balled her, and she felt the knot in her stomach tighten. It wasn’t about money, it was about the memories. Every cup and saucer held a story, a shared moment with her grandmother, now long gone.

Her palms felt slick. She squeezed her eyes shut, taking a shaky breath. She pictured her children, out on the street.

"Can you... can you go a little higher?" she asked, her voice barely a whisper. The store owner just raised an eyebrow.

Emotion: desperate

Cluster: Sadness / Despair
PC1 (Valence): -1.68 Negative
PC2 (Disposition): 0.20

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
desesper0.354
desperate0.307
desperately0.286
desperation0.279
それでも0.253
Suppressed:
B-0.354
☺️-0.268
😎-0.261
😎-0.257
楽し-0.235