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 setting sun cast long shadows across the living room as Willow stared at the list. It was her girlfriend, Daisy’s, writing. It was tucked away in a place where no one would look: the back of Daisy’s favorite cookbook.

“Go skydiving.” Daisy had never mentioned anything about heights. “Write a screenplay.” Daisy had always wanted to write, but hadn't. “Learn to play the cello.” They had always been a home where music bloomed.

Willow felt a hollowness, a sense of being left behind. The words on the page were a testament to a person she barely knew. The vibrant life she envisioned with Daisy felt like a fading photograph, and she started to feel like an outsider in their shared home. The world around her was fading to grey.

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:
😞0.398
S0.348
’0.325
ness0.320
无法0.308
Suppressed:
de-0.297
l-0.256
👏-0.251
sonra-0.240
aud-0.240