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).

Eliza walked through the quad, the familiar landscape seeming foreign and distant. The cheerful chatter of students playing frisbee felt like a soundtrack to someone else’s life. Her advisor, Dr. Lee, had accepted a position overseas.

She kept replaying the email in her head. It was a good opportunity for Dr. Lee. Why did it have to feel so difficult? She felt it in her bones, a deep and unyielding ache.

She’d spent the last year working on her research. Now, she was lost, unsure of what to do next. The sunlight, previously a source of joy, now felt harsh, mocking her unease. The vibrant colors of autumn seemed to amplify her internal grayness.

She sat on a bench and watched the squirrels chase each other, their energy a stark contrast to her own inertia.

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