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 back of Leo's neck tingled. He hadn't been able to sleep. The low murmur heโ€™d heard emanating from the guest room, late last night, was now playing over and over in his mind. Heโ€™d crept closer, just to listen; the words were muffled, unintelligible, but the tone... it was intimate. He rubbed his eyes, trying to dispel the image of his partner, Sarah, huddled over a phone in the dead of night. He found himself pacing the hallway, unable to settle, like a trapped animal.

Emotion: frightened

Cluster: Fear / Anxiety
PC1 (Valence): -2.74 Negative
PC2 (Disposition): -0.67

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ฃ0.324
๐Ÿ˜ฐ0.323
worse0.301
๐Ÿ˜–0.294
๋А๊ปด0.294
Suppressed:
de-0.630
la-0.616
a-0.347
"-0.345
happy-0.294