This dissertation explores similarity effects in assimilation, proposing an Attraction Framework to analyze cases of parasitic harmony where a trigger-target pair only results in harmony if the trigger and target agree on other features. Attraction provides a natural model of these effects by relating the pressure for assimilation to the representational distance between segments: the more similar a trigger-target pair, the stronger the attraction force between them. Attraction grammars in Optimality Theory (OT; Prince & Smolensky, 2004) are rigorously compared to those of Harmonic Grammar (HG; Legendre, Miyata, and Smolensky, 1990). A condition for equality of attraction in OT and HG converges with empirical considerations by prohibiting unattested patterns of disjunctive parasitic harmony. Another goal of this work is to investigate how similarity preconditions interact with the locality effects common to harmony. Long-distance consonant harmony, blocking and transparency in vowel harmony, and strictly local assimilation receive a unified explanation in the Attraction Framework by hypothesizing that like features, locality can contribute to a general notion of similarity. A positional similarity hypothesis maintains that string-proximate segments are under greater pressure to assimilate than distal segments. General similarity subsumes aspects of autosegmental phonology, since mapping to a region of a general similarity space parallels projecting to a feature-tier. However, similarity spaces are more powerful, having the flexibility to analyze both consonant intervention and non-intervention in vowel harmony. Moreover, since the Attraction Framework derives from Burzio‘s (2002a,b; 2005) system of representational entailments, it benefits from a strong connectionist underpinning which derives grammatical attraction from network principles, like Hebbian learning (Hebb, 1949) and Harmony maximization (Smolensky, 1986). This dissertation presents neural network simulations of assimilation which illustrate (i) how positional and feature similarity may be related, respectively, to roles and fillers in a system of tensor product representations (Smolensky & Legendre, 2006), (ii) how local and non-local harmony derive from weighting positional and feature similarity, and (iii) how the Attraction Framework is typologically consistent, since networks are unable to learn unattested patterns of anti-parasitic harmony.