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 grand, antique clock in the center of the hall ticked, each tick a hammer blow against Arthurโ€™s already fragile composure. His sister, Beatrice, was already celebrating. A controlling stake in the family business, a seat at the table. Everything he felt entitled to himself.

He held the thin, fragile box that had been given to him. A small, tarnished silver locket. He felt a hot flush crawl up his neck.

Inside was a faded photograph of his father, younger than he remembered him, holding a small boy. His little brother, who had died before Arthur was born.

He knew what was expected. He knew what he was. He was a failure. He had never been able to be happy.

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
้€ƒ0.297
๐Ÿ˜ž0.295
Suppressed:
de-0.539
que-0.300
๐Ÿ˜-0.288
(!)-0.269
๐Ÿคฉ-0.242