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 string quartet’s rendition of “Can’t Help Falling in Love” wafted through the air, and Amelia felt a lump form in her throat. She hadn’t expected to feel quite like this. Seeing David, standing near the bar, somehow felt like a punch to the gut. It had been nearly two years, a lifetime in the grand scheme of things, but the memories, like unwelcome guests, crowded her mind.

She clutched her champagne flute a little too tightly, the delicate glass pressing into her palm. The wedding was beautiful; the flowers, the lights, the happy couple. Everything, except for this unexpected encounter.

“Amelia, you alright?” Sarah, the bride, drifted over, her smile radiant. Amelia forced a smile back, her cheeks aching. “Just… a bit warm, I think.”

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396