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 heat in the attic was stifling, but Emily didn't mind. She’d always loved exploring. She unearthed a collection of handwritten journals, bound in leather, filled with tight, meticulous handwriting.

She tentatively opened one. The first entry was a list of birds that the writer had seen in their garden. She read on, the words transporting her. The writer, a woman, had meticulously cataloged her life – her joys, her sorrows, her quiet moments of contemplation. Emily was captivated.

She felt a kinship with this stranger, a shared experience of the human condition. She carefully placed the journals in a box. She was eager to understand the woman that had come before her.

Emotion: sentimental

Cluster: Nostalgia / Reflection
PC1 (Valence): 0.89 Positive
PC2 (Disposition): -1.58

Role in Research

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

Logit Lens (Layer 40)

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

Promoted:
L0.677
fondly0.567
memories0.503
曾0.488
reminis0.466
Suppressed:
either-0.515
or-0.488
[]-0.473
--0.408
не-0.396