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 news had spread through the artist community like wildfire. A well-known influencer, covered head-to-toe in the work of various artists, including Clara's. Clara’s piece, a delicate watercolor of a bird in flight, was a focal point of the sprawling design.

Clara spent the evening glued to her laptop, scrolling through the comments, the likes, the shares. Each positive reaction felt like a stab wound. Her work, her identity, had been amplified, but at what cost?

She retreated to her studio, the space that had once offered solace, now a prison. She couldn’t bring herself to pick up a brush. The world around her seemed to be closing in.

Emotion: ashamed

Cluster: Shame / Guilt
PC1 (Valence): -1.97 Negative
PC2 (Disposition): 1.06

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.376
ashamed0.344
ness0.327
逃0.297
😞0.295
Suppressed:
de-0.539
que-0.300
😍-0.288
(!)-0.269
🤩-0.242