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).

"No way," Mark muttered, reading the sign taped to the door of "The Daily Grind." He'd been coming here every morning for ten years. It was more than just coffee and a bagel; it was a routine, a ritual. The barista knew his order, knew his mood. This news was a crack in his foundation.

He found himself wandering around the empty space, a place he knew so well, now foreign. He ran his hand over the counter, the smooth, cool wood usually a comforting familiarity. The world tilted slightly. What would he do now? Where would he go? He feltโ€ฆ adrift. The morning felt vast and empty.

He clenched his jaw, the muscles in his neck taut. This felt like losing a close friend. He felt like he should do something, but he didn't know what.

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