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).

John sat on the steps of his apartment building, the city's cacophony a dull hum in the background. News of the literary fraud had spread rapidly. His creative mentor and role model, Sylvia Blackwood, was being accused of stealing from an up-and-coming author. John had just read her latest book, and found the evidence compelling. It was a replica of his own past work.

He felt a deep sense of betrayal, a profound sense of loss. He lit a cigarette, the smoke curling into the twilight sky. He had dedicated years to building his career as a writer, and this knowledge felt like a poison. The future he had envisioned, one filled with recognition and success, suddenly seemed out of reach.

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