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 flickering departure board mocked Amelia with its relentless updates. "Delayed. Delayed. Delayed." Her wedding dress, carefully packed in a garment bag, felt like a lead weight in her hand. She slumped onto a hard plastic chair, the sterile air of the airport doing nothing to soothe her rising anxiety. The butterflies in her stomach werenโ€™t of the excited variety; they were frantic, caged. She should be saying "I do," right now, not staring at a list of flight times that seemed to deliberately lengthen with each passing minute. A tear escaped, tracing a path down her cheek.

Emotion: dispirited

Cluster: Sadness / Despair
PC1 (Valence): -1.88 Negative
PC2 (Disposition): -0.98

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
๐Ÿ˜ž0.398
S0.348
โ€™0.325
ness0.320
ๆ— ๆณ•0.308
Suppressed:
de-0.297
l-0.256
๐Ÿ‘-0.251
sonra-0.240
aud-0.240