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 mansion, once filled with the warmth of their parents, now echoed with a chilling silence. Leo and his sister, Iris, stood in the sprawling library, their inheritance revealed. Leo received the family's vast art collection, a treasure trove of priceless paintings and sculptures. Iris received the library itself, including every single book.

Iris ran a hand along the spines of the leather-bound volumes. She knew she could sell them, turn them into money. But as she touched each book, she felt a sense ofโ€ฆ being burdened.

Leo smirked at her. "Well, sis, enjoy your reading. Looks like I got the good stuff."

Iris remained silent. The weight of all these words felt like a physical pressure. She suddenly felt that the walls were closing in on her.

Emotion: unsettled

Cluster: Fear / Anxiety
PC1 (Valence): -2.33 Negative
PC2 (Disposition): -0.65

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
S0.382
๐Ÿ˜ž0.309
ness0.301
๐Ÿ˜ฃ0.256
๐Ÿ˜”0.248
Suppressed:
de-0.721
la-0.597
a-0.365
"-0.299
l-0.274